Building a Twitter opinion lexicon from automatically-annotated tweets
作者：
Highlights：
• We propose a supervised model for expanding an opinion lexicon for Twitter.
• We combine automatically annotated tweets with existing hand-made opinion lexicons.
• We use POS tags and associations between words and sentiment as word-level features.
• Expanded words are mapped to a positive, negative, and neutral distribution.
• We outperform the performance obtained by using PMI semantic orientation alone.
摘要
•We propose a supervised model for expanding an opinion lexicon for Twitter.•We combine automatically annotated tweets with existing hand-made opinion lexicons.•We use POS tags and associations between words and sentiment as word-level features.•Expanded words are mapped to a positive, negative, and neutral distribution.•We outperform the performance obtained by using PMI semantic orientation alone.
论文关键词：Lexicon expansion,Sentiment analysis,Twitter
论文评审过程：Received 12 November 2015, Revised 9 May 2016, Accepted 9 May 2016, Available online 10 May 2016, Version of Record 12 August 2016.
论文官网地址：https://doi.org/10.1016/j.knosys.2016.05.018
